{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hilcodec-high-fidelity-and-lightweight-neural","title":"HILCodec: High-Fidelity and Lightweight Neural Audio Codec","arxiv_id":"2405.04752","date":"2024-05-08","proceeding":null,"authors":["Sunghwan Ahn","Beom Jun Woo","Min Hyun Han","Chanyeong Moon","Nam Soo Kim"],"abstract":"The recent advancement of end-to-end neural audio codecs enables compressing audio at very low bitrates while reconstructing the output audio with high fidelity. Nonetheless, such improvements often come at the cost of increased model complexity. In this paper, we identify and address the problems of existing neural audio codecs. We show that the performance of the SEANet-based codec does not increase consistently as the network depth increases. We analyze the root cause of such a phenomenon and suggest a variance-constrained design. Also, we reveal various distortions in previous waveform domain discriminators and propose a novel distortion-free discriminator. The resulting model, HILCodec, is a real-time streaming audio codec that demonstrates state-of-the-art quality across various bitrates and audio types.","url_abs":"https://arxiv.org/abs/2405.04752v2","url_pdf":"https://arxiv.org/pdf/2405.04752v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hilcodec-high-fidelity-and-lightweight-neural","repo_url":"https://github.com/aask1357/hilcodec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.04752","atlas_url":"https://app.syntology.ai/?focus=2405.04752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04752"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aask1357/hilcodec","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":10,"unverified":2},"by_repo_kind":{"official":{"samples":12,"ran":10,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7127cd68fc0b6181","entry":"SConv1d","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/causal_layers.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/causal_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7127cd68fc0b6181"}},{"code_sha256_prefix":"2c73c22b72590d06","entry":"SConvTranspose1d","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/causal_layers.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/causal_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c73c22b72590d06"}},{"code_sha256_prefix":"1473010bb86abf65","entry":"get_2d_padding","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/discriminators.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/discriminators.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1473010bb86abf65"}},{"code_sha256_prefix":"e28f4ff393bc05c9","entry":"get_padding","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/avocodo.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/avocodo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e28f4ff393bc05c9"}},{"code_sha256_prefix":"5a866a6652d3e867","entry":"kmeans","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/vector_quantize.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/vector_quantize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a866a6652d3e867"}},{"code_sha256_prefix":"0254d06d15bac873","entry":"l2norm","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/vector_quantize.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/vector_quantize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0254d06d15bac873"}},{"code_sha256_prefix":"0a1977d56c184638","entry":"log_clip","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/losses.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a1977d56c184638"}},{"code_sha256_prefix":"da36a93a8ef96944","entry":"mel_scale","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/losses.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da36a93a8ef96944"}},{"code_sha256_prefix":"221f45f54c4ff8f5","entry":"mel_spectrogram","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/losses.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"221f45f54c4ff8f5"}},{"code_sha256_prefix":"01c3ffb2465073f7","entry":"sample_vectors","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/vector_quantize.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/vector_quantize.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01c3ffb2465073f7"}},{"code_sha256_prefix":"8d9aa381c6147164","entry":"get_extra_padding_for_conv1d","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/modules/conv.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/modules/conv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d9aa381c6147164"}},{"code_sha256_prefix":"5871424a686367d5","entry":"get_norm_module","repo":"aask1357/hilcodec","repo_kind":"official","path":"models/hilcodec/modules/conv.py","file_url":"https://github.com/aask1357/hilcodec/blob/HEAD/models/hilcodec/modules/conv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5871424a686367d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}